Pattern Recognition and
Image Processing Group
Institute of Computer Graphics and Algorithms
PRIP Fakultät für Informatik, TU Wien Technische Universität Wien Fakultät für Informatik

Welcome to PRIP

PRIP group members

Modern sensors, like digital photo and video cameras, measure huge amounts of data day-by-day. Pattern Recognition and Image Processing aims at the extraction of information from such data.

Usually, the information to be extracted is related to pieces of data from the same environment that gives them meaning. Typical applications are tasks like autonomous navigation, the detection of anomalies in medical images or the prediction of an eruption of a volcano.

Simple tasks like the detection of human faces are already solved and solutions are commercially available in digital cameras. However, there is still a large number of complex tasks that require the system to incorporate knowledge to be efficiently used to enhance the recognition results and to give semantically appropriate interpretations. Such knowledge could be about the characteristics of the camera system, the composition and structure of the environment or the available processing strategies.

The large amount of data to be processed requires sophisticated representations that are both efficient and robust with respect to noise and distortions in the measurements.

Some problems may seem hopeless to solve at a first glance, but there are wonderful "natural" systems solving extremely hard tasks nearly effortlessly. We can learn by better understanding the human/biological perception mechanisms.



Are you looking for an interesting topic for your project, bachelor thesis or diploma/master's thesis?

In the following, you can find currently open topics, where we are actively searching for interested and motivated students.
For more information about the different options for projects and theses at PRIP click here.

Development of a pose-independent representation of 2D horse shapes
Master's thesis/Practicum/Bachelor thesis

The Spanish Riding School with its Lipizzan horses is one of the most famous tourist attractions in Vienna. In breeding, it is desirable to objectively evaluate the traits of a Lipizzan horse based on quantitative measurements. Unfortunately, traditional approaches of measurement lead to a low repeatability rate due to pose changes of the horse and/or differences between the measurement techniques of different people.

The aim of this thesis is to develop a representation of a 2D horse shape, which is independent of pose OR to develop an approach which is able to “normalize” the current pose of a horse to a standard-pose.

For detailed information see announcement. horse icon

Contact: Mail: webmaster(at) | Tel: +43.1.58801.18661 | Fax : +43.1.58801.18697
2014 PRIP, Impressum
This page is maintained by Webmaster ( webmaster(at) ) and was last modified on 29. March 2017 14:26